Liquid AI releases LFM2.5-24B-A2B, a reasoning model for on-device agents
Liquid AI introduced LFM2.5-24B-A2B, a 24B-parameter reasoning model with just 2B active parameters, built to run fast, private agents on local hardware.
AI Desk1 min read
Tag
Every The Latent Daily story, tool, model and resource tagged “Small Models”.
Liquid AI introduced LFM2.5-24B-A2B, a 24B-parameter reasoning model with just 2B active parameters, built to run fast, private agents on local hardware.
AI Desk1 min read
Distillation trains a compact "student" model to imitate a large "teacher". How it works, why it powers today's small models, and its legal and quality limits.
AI Desk3 min read
Google's family of lightweight open models from 1B to 27B parameters, with image input on larger sizes, 128K context and support for 140+ languages.
A tiny 82-million-parameter open text-to-speech model with natural-sounding voices, small enough to run quickly on ordinary hardware.
Microsoft's 14-billion-parameter small language model trained heavily on high-quality synthetic data, strong at math and reasoning for its size.